Structural Deep Clustering Network

Abstract

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful representation ability of deep learning, e.g., autoencoder, suggesting that learning an effective representation for clustering is a crucial requirement. The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning. Motivated by the great success of Graph Convolutional Network (GCN) in encoding the graph structure, we propose a Structural Deep Clustering Network (SDCN) to integrate the structural information into deep clustering. Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model. In this way, the multiple structures of data, from low-order to high-order, are naturally combined with the multiple representations learned by autoencoder. Furthermore, we theoretically analyze the delivery operator, i.e., with the delivery operator, GCN improves the autoencoder-specific representation as a high-order graph regularization constraint and autoencoder helps alleviate the over-smoothing problem in GCN. Through comprehensive experiments, we demonstrate that our propose model can consistently perform better over the state-of-the-art techniques.

Published at The Web Conference (WWW) 2020, full paper

Cited by in corpus (26)

• A Comprehensive Survey on Community Detection with Deep Learning
• Consistent Multiple Graph Embedding for Multi-View Clustering
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• A Diffusion model for POI recommendation
• Incomplete Multi-view Clustering via Cross-view Relation Transfer
• Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework
• Self-supervised Contrastive Attributed Graph Clustering
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
• CGC: Contrastive Graph Clustering for Community Detection and Tracking
• X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
• ROD: Reception-aware Online Distillation for Sparse Graphs
• RobustECD: Enhancement of Network Structure for Robust Community Detection
• Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets
• Relational Thematic Clustering with Mutually Preferred Neighbors
• Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning
• NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• Reliable Node Similarity Matrix Guided Contrastive Graph Clustering
• CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
• Seeing All From a Few: Nodes Selection Using Graph Pooling for Graph Clustering
• Incorporating Higher-order Structural Information for Graph Clustering
• Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
• Attention-driven Graph Clustering Network
• Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning
• Scalable Deep Metric Learning on Attributed Graphs
• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion